Triple
T3378468
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | K-9 |
E71121
|
entity |
| Predicate | voicedBy |
P2181
|
FINISHED |
| Object | John Leeson |
E199479
|
NE FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: John Leeson | Statement: [K-9, voicedBy, John Leeson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Leeson Context triple: [K-9, voicedBy, John Leeson]
-
A.
John Leeson
chosen
John Leeson is a British actor best known for voicing the robotic dog K-9 in the Doctor Who television franchise.
-
B.
Geoffrey Haslam
Geoffrey Haslam is a record producer best known for his work on Bette Midler’s debut album "The Divine Miss M."
-
C.
Graham Stanton
Graham Stanton is a senior Royal Air Force officer who served as Air Officer Commanding-in-Chief of Fighter Command.
-
D.
Richard Sibson
Richard Sibson is a distinguished geologist recognized for his influential work on fault mechanics and earthquake processes.
-
E.
Douglas Slocombe
Douglas Slocombe was a renowned British cinematographer celebrated for his work on numerous classic films, including major entries in the Indiana Jones series.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69ad85a7f80c8190a05e43013f298942 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb2eacb5c81908071a1dacc9a897a |
completed | March 8, 2026, 5:33 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b503d6cd9c81908acb288091503ec1 |
completed | March 14, 2026, 6:44 a.m. |
Created at: March 8, 2026, 3:14 p.m.